Spatial understanding has been a challenging task for existing Multi-modal Large Language Models~(MLLMs). Previous methods leverage large-scale MLLM finetuning to enhance MLLM's spatial understanding ability. In this paper, we present a data-efficient approach. We propose a LLM agent system with strong and advanced spatial reasoning ability, which can be used to solve the challenging spatial question answering task in complex indoor warehouse scenarios. Our system integrates multiple tools that allow the LLM agent to conduct spatial reasoning and API tools interaction to answer the given complicated spatial question. Extensive evaluations on the 2025 AI City Challenge Physical AI Spatial Intelligence Warehouse dataset demonstrate that our system achieves high accuracy and efficiency in tasks such as object retrieval, counting, and distance estimation. The code is available at: https://github.com/hsiangwei0903/SpatialAgent
@article{arxiv.2507.10778,
title = {Warehouse Spatial Question Answering with LLM Agent},
author = {Hsiang-Wei Huang and Jen-Hao Cheng and Kuang-Ming Chen and Cheng-Yen Yang and Bahaa Alattar and Yi-Ru Lin and Pyongkun Kim and Sangwon Kim and Kwangju Kim and Chung-I Huang and Jenq-Neng Hwang},
journal= {arXiv preprint arXiv:2507.10778},
year = {2025}
}
Comments
1st Place Solution of the 9th AI City Challenge Track 3